We describe a way to make a hypermedia meeting record from multimedia meeting documents by automatically generating links through image matching. In particular, we look at video recordings and scanned paper handouts of presentation slides with ink annotations. The algorithm that we employ is the Discrete Cosine Transform (DCT). Interactions with multipath links and paper interfaces are discussed.

We present and interactive system that allows a user to locate regions of video that are similar to a video query. Thus segments of video can be found by simply providing an example of the video of interest. The user selects a video segment for the query from either a static frame-based interface or a video player. A statistical model of the query is calculated on-the-fly, and is used to find similar regions of video. The similarity measure is based on a Gaussian model of reduced frame image transform coefficients. Similarity in a single video is displayed in the Metadata Media Player. The player can be used to navigate through the video by jumping between regions of similarity. Similarity can be rapidly calculated for multiple video files as well. These results are displayed in MBase, a Web-based video browser that allows similarity in multiple video files to be visualized simultaneously.

This paper presents a method for generating compact pictorial summarizations of video. We developed a novel approach for selecting still images from a video suitable for summarizing the video and for providing entry points into it. Images are laid out in a compact, visually pleasing display reminiscent of a comic book or Japanese manga. Users can explore the video by interacting with the presented summary. Links from each keyframe start video playback and/or present additional detail. Captions can be added to presentation frames to include commentary or descriptions such as the minutes of a recorded meeting. We conducted a study to compare variants of our summarization technique. The study participants judged the manga summary to be significantly better than the other two conditions with respect to their suitability for summaries and navigation, and their visual appeal.

This paper presents methods for automatically creating pictorial video summaries that resemble comic books. The relative importance of video segments is computed from their length and novelty. Image and audio analysis is used to automatically detect and emphasize meaningful events. Based on this importance measure, we choose relevant keyframes. Selected keyframes are sized by importance, and then efficiently packed into a pictorial summary. We present a quantitative measure of how well a summary captures the salient events in a video, and show how it can be used to improve our summaries. The result is a compact and visually pleasing summary that captures semantically important events, and is suitable for printing or Web access. Such a summary can be further enhanced by including text captions derived from OCR or other methods. We describe how the automatically generated summaries are used to simplify access to a large collection of videos.

In our Portholes research, we found that users needed to have a sense of being in public and to know who can see them (audience) and who is looking currently at them (lookback). Two redesigns of the Portholes display present a 3D theater view of the audience. Different sections display core team members, non-core team members and lookback. An experiment determined that people have strong preferences about audience information and how it should be displayed. Layout preferences are varied, but unfolding techniques and cluster analysis reveal that these preference perspectives fall into four groups of similar preferences.

When reviewing collections of video such as recorded meetings or presentations, users are often interested only in an overview or short segments of these documents. We present techniques that use automatic feature analysis, such as slide detection and applause detection, to help locate the desired video and to navigate to regions of interest within it. We built a web-based interface that graphically presents information about the contents of each video in a collection such as its keyframes and the distribution of a particular feature over time. A media player is tightly integrated with the web interface. It supports navigation within a selected file by visualiz-ing confidence scores for the presence of features and by using them as index points. We conducted a user study to refine the usability of these tools.

This paper describes techniques for classifying video frames using statistical models of reduced DCT or Hadamard transform coefficients. When decimated in time and reduced using truncation or principal component analysis, transform coefficients taken across an entire frame image allow rapid modeling, segmentation, and similarity calculation. Unlike color-histogram metrics, this approach models image composition and works on grayscale images. Modeling the statistics of the transformed video frame images gives a likelihood measure that allows video to be segmented, classified, and ranked by similarity for retrieval. Experiments are presented that show an 87% correct classification rate for different classes. Applications are presented including a content-aware video browser.

In many hierarchical companies, reports from several independent groups must be merged to form a single, company-wide report. This paper describes a process and system for creating and structuring such reports and for propagating contributions up the organization. The system has been in regular use, in-house, by about 30 users for over a year to create monthly status reports. Our experiences indicate that it is possible to change a monthly reporting practice so that the system is easy to use, improves the quality of the written report, fosters collaboration across projects and creates a corporate memory for the company. These results were achieved as a consequence of our design effort to directly support the hierarchical and collaborative process of creating and assembling the report within the organization. User feedback has led to many improvements in the usability and functionality of the system. Further enhancements using information retrieval and text summarization techniques are in progress.

The Digestor system automatically converts web-based documents designed for desktop viewing into formats appropriate for handheld devices with small display screens, such as Palm-PCs, PDAs, and cellular phones. Digestor employs a heuristic planning algorithm and a set of structural page transformations to produce the "best" looking document for a given display size. Digestor can also be instructed, via a scripting language, to render portions of documents, thereby avoiding navigation through many screens of information. Two versions of Digestor have been deployed, one that re-authors HTML into HTML for conventional browsers, and one that converts HTML into HDML for Unwired Planet's micro-browsers. Digestor provides a crucial technology for rapidly accessing, scanning and processing information from arbitrary web-based documents from any location reachable by wired or unwired communication.

In accessing large collections of digitized videos, it is often difficult to find both the appropriate video file and the portion of the video that is of interest. This paper describes a novel technique for determining keyframes that are different from each other and provide a good representation of the whole video. We use keyframes to distinguish videos from each other, to summarize videos, and to provide access points into them. The technique can determine any number of keyframes by clustering the frames in a video and by selecting a representative frame from each cluster. Temporal constraints are used to filter out some clusters and to determine the representative frame for a cluster. Desirable visual features can be emphasized in the set of keyframes. An application for browsing a collection of videos makes use of the keyframes to support skimming and to provide visual summaries.

Many techniques can extract information from an multimedia stream, such as speaker identity or shot boundaries. We present a browser that uses this information to navigate through stored media. Because automatically-derived information is not wholly reliable, it is transformed into a time-dependent "confidence score." When presented graphically, confidence scores enable users to make informed decisions about regions of interest in the media, so that non-interesting areas may be skipped. Additionally, index points may be determined automatically for easy navigation, selection, editing, and annotation and will support analysis types other than the speaker identification and shot detection used here.

The World Wide Web is often viewed as the latest and most user friendly way of providing information over the Internet (i.e., server of documents). It is not customarily viewed as a platform for developing and deploying applications. In this tutorial, we introduce, demonstrate, and discuss how Web technologies like CGI scripts, Javascript, and Java can be used in combination with Web browsers to design, create, distribute and execute collaborative applications. We discuss constraints with the Web approach as well as recent extensions that support application development.

The prevalence of audio and video options on computers, coupled with the promise of bandwidth, have many prognosticators predicting a revolution in human communications. But what if the revolution materializes and no users show up? We were confronted with this question when we began deploying and studying the use of a video-based, background awareness application within our organization. Repeatedly, new users raised strong concerns about self-presentation, surveillance, privacy, video snapshots, and lack of audience cues. We describe how we addressed these concerns by evolving the application. As a consequence, we are also redesigning the user interface to the application.

The phenomenal interest and growth of the World Wide Web as an application server has pushed the Web model to its limits. Specifically, the Web offers limited interactivity and versatility as a platform for networked applications. One major challenge for the HCI community is to determine how to improve the human-computer interface for Web-based applications. This paper focuses on a significant Web deficiency - supporting truly interactive and dynamic form-based input. We propose a well-worked form interaction abstraction that alleviates this Web deficiency. We describe how the abstraction is seamlessly integrated into the Web framework by leveraging on the virtues of the Web and fitting within the interaction and usage model of the Web.

Video-based awareness tools increase familiarity among remote group members and provide pre-communication information. Low-cost iconic indicators provide less but more succinct information than video images while preserving privacy. Observations of and feedback from users of our video awareness tool suggest that an activity sensing feature along with a variety of privacy options combines advantages of both the video images and iconic indicator approaches. We introduced the activity sensing feature in response to user requests. It derives activity information from video images and provides options to control privacy and improves the usability of video-based awareness tools.